deepspeedai · yisustc · Mar 6, 2025 · Mar 7, 2025 · Mar 10, 2025 · Mar 11, 2025
@@ -42,7 +42,7 @@ jobs:
           git clone https://github.com/huggingface/transformers
           cd transformers
           # if needed switch to the last known good SHA until transformers@master is fixed
-          git checkout 981c276
+          # git checkout 981c276
           git rev-parse --short HEAD
           pip install .
 
@@ -59,5 +59,5 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -n 4 unit/ --torch_ver="2.6"
-          HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -m 'sequential' unit/ --torch_ver="2.6"
+          HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -n 4 unit/ --torch_ver="2.7"
+          HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -m 'sequential' unit/ --torch_ver="2.7"
@@ -21,7 +21,7 @@ jobs:
     # The type of runner that the job will run on
     runs-on: [self-hosted, intel, gaudi2]
     container:
-      image: vault.habana.ai/gaudi-docker/1.19.0/ubuntu22.04/habanalabs/pytorch-installer-2.5.1:latest
+      image: vault.habana.ai/gaudi-docker/1.20.0/ubuntu22.04/habanalabs/pytorch-installer-2.6.0:latest
       ports:
         - 80
       options: --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice
@@ -45,6 +45,8 @@ jobs:
         test_zero_leaf_module.py
         test_zero_offloadpp.py
         test_zero_tiled.py
+        test_autotp_training.py
+        test_ulysses.py
 
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:

@@ -39,7 +39,7 @@ jobs:
     # The type of runner that the job will run on
     runs-on: [self-hosted, intel, gaudi2]
     container:
-      image: vault.habana.ai/gaudi-docker/1.19.0/ubuntu22.04/habanalabs/pytorch-installer-2.5.1:latest
+      image: vault.habana.ai/gaudi-docker/1.20.0/ubuntu22.04/habanalabs/pytorch-installer-2.6.0:latest
       ports:
         - 80
       options: --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice
@@ -94,6 +94,8 @@ jobs:
         test_zero_nesting_init.py
         test_zeropp.py
         (test_zero.py and (TestZero3ParamPartitioningLargeParam or TestZero3ParamPartitioningLargeParam))
+        (test_linear.py and (TestLoRALinear or TestBasicLinear))
+        (test_ctx.py and TestEngine)
 
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:
@@ -112,7 +114,7 @@ jobs:
           git clone https://github.com/huggingface/transformers
           cd transformers
           # if needed switch to the last known good SHA until transformers@master is fixed
-          git checkout 981c276
+          # git checkout 981c276
           git rev-parse --short HEAD
           pip install .
 

@@ -23,7 +23,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:24.09-py3
+      image: nvcr.io/nvidia/pytorch:24.12-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -43,7 +43,7 @@ jobs:
           git clone https://github.com/huggingface/transformers
           cd transformers
           # if you need to use an older transformers version temporarily in case of breakage
-          git checkout 981c276
+          # git checkout 981c276
           git rev-parse --short HEAD
           python -m pip install .
       - name: Install deepspeed
@@ -58,8 +58,8 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.5" --cuda_ver="12"
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.5" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.6" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.6" --cuda_ver="12"
       - name: MII unit tests
         run: |
           BRANCH="main"

@@ -18,7 +18,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:24.09-py3
+      image: nvcr.io/nvidia/pytorch:24.12-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -53,7 +53,7 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF unit/sequence_parallelism/test_ulysses.py --torch_ver="2.5" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF unit/sequence_parallelism/test_ulysses.py --torch_ver="2.6" --cuda_ver="12"
       - name: Open GitHub issue if nightly CI fails
         if: ${{ failure() && (github.event_name == 'schedule') }}
         uses: JasonEtco/create-an-issue@v2

@@ -11,7 +11,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:24.09-py3
+      image: nvcr.io/nvidia/pytorch:24.12-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -50,4 +50,4 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.5" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.6" --cuda_ver="12"
@@ -36,7 +36,7 @@ jobs:
             #python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
         - name: Compile DeepSpeed Ops
           run: |
-            DS_ACCELERATOR=cuda DS_ENABLE_NINJA=1 TORCH_CUDA_ARCH_LIST="7.0;7.5;8.0" DS_BUILD_OPS=1 DS_BUILD_SPARSE_ATTN=0 DS_BUILD_FP_QUANTIZER=0 DS_BUILD_CUTLASS_OPS=0 DS_BUILD_GDS=0 DS_BUILD_RAGGED_DEVICE_OPS=0 DS_BUILD_EVOFORMER_ATTN=0 pip3 install .
+            DS_ACCELERATOR=cuda DS_ENABLE_NINJA=1 TORCH_CUDA_ARCH_LIST="7.0;7.5;8.0" DS_BUILD_OPS=1 DS_BUILD_SPARSE_ATTN=0 DS_BUILD_FP_QUANTIZER=0 DS_BUILD_CUTLASS_OPS=0 DS_BUILD_GDS=0 DS_BUILD_RAGGED_DEVICE_OPS=0 DS_BUILD_EVOFORMER_ATTN=0 DS_BUILD_DEEP_COMPILE=0 pip3 install .
         - name: DS Report
           run: |
              ds_report
@@ -44,7 +44,7 @@ jobs:
 
       - name: Install deepspeed
         run: |
-          pip install .[dev,1bit,autotuning]
+          pip install .[dev,1bit,autotuning,deepcompile]
           ds_report
 
       - name: Python environment

@@ -37,7 +37,7 @@ jobs:
           git clone https://github.com/huggingface/transformers
           cd transformers
           # if needed switch to the last known good SHA until transformers@master is fixed
-          git checkout 981c276
+          # git checkout 981c276
           git rev-parse --short HEAD
           pip install .
 

@@ -6,7 +6,9 @@ runs:
     - id: update-env
       run: |
         sudo apt-get update
-        sudo apt-get install -y libaio-dev
+        # Temporary disable nvme UTs
+        # sudo apt-get install -y libaio-dev
+        sudo apt remove -y libaio-dev
         python -m pip install --user --upgrade pip
         python -m pip install --user --upgrade virtualenv
       shell: bash

@@ -36,7 +36,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, intel, xpu]
     container:
-      image: intel/oneapi-basekit:2025.0.1-0-devel-ubuntu24.04
+      image: intel/oneapi-basekit:2025.0.2-0-devel-ubuntu22.04
       ports:
         - 80
       options: --privileged -it --rm --device /dev/dri:/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --ipc=host --cap-add=ALL
@@ -47,20 +47,16 @@ jobs:
       shell: bash
       run: |
         apt-get update
-        apt-get install clinfo libaio-dev python3-pip python3.12-venv -y
-        python3 -m venv ~/ds_env
-        source ~/ds_env/bin/activate
-        pip install torch==2.5.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torch/
-        pip install intel-extension-for-pytorch==2.5.10+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/intel-extension-for-pytorch/
-        pip install oneccl_bind_pt==2.5.0+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/oneccl-bind-pt/
-        pip install torchvision==0.20.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torchvision/
-        pip install py-cpuinfo numpy
+        apt-get install -y python3.11 python3.11-dev python3-pip clinfo libaio-dev
+        pip install --upgrade pip
+        pip install py-cpuinfo
+        pip install torch==2.7.0 torchvision==0.22.0 torchaudio==2.7.0 --index-url https://download.pytorch.org/whl/xpu
+        pip install intel-extension-for-pytorch==2.7.10+xpu oneccl_bind_pt==2.7.0+xpu --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us
         pip install .[dev,autotuning]
 
     - name: Check container state
       shell: bash
       run: |
-        source ~/ds_env/bin/activate
         ldd --version
         ds_report
         python3 -c "import torch; print('torch:', torch.__version__, torch)"
@@ -71,8 +67,9 @@ jobs:
     - name: Unit tests
       shell: bash
       run: |
-        source ~/ds_env/bin/activate
         cd tests/unit
+        export FI_PROVIDER="tcp"
+        export I_MPI_SHM=off
         pytest --verbose accelerator/*
         pytest --verbose autotuning/*
         pytest --verbose checkpoint/test_reshape_checkpoint.py

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -19,6 +19,12 @@ If a formatting test fails, it will fix the modified code in place and abort
 the `git commit`. After looking over the changes, you can `git add <modified files>`
 and then repeat the previous `git commit` command.
 
+You can also run:
+```
+make format
+```
+which will do the same as above, and it'll also automatically build a `venv` python environment if you
+don't already have one, which will isolate the requirements of this project from requirements of other projects.
 
 ## Testing
 DeepSpeed tracks two types of tests: unit tests and more costly model convergence tests.
@@ -38,6 +44,11 @@ You can also provide the `-v` flag to `pytest` to see additional information abo
 tests. Note that [pytest-forked](https://github.com/pytest-dev/pytest-forked) and the
 `--forked` flag are required to test CUDA functionality in distributed tests.
 
+You can also run:
+```
+make test
+```
+
 ### Model Tests
 To execute model tests, first [install DeepSpeed](#installation). The
 [DeepSpeedExamples](https://github.com/deepspeedai/DeepSpeedExamples/) repository is cloned
@@ -48,16 +59,15 @@ pytest run_sanity_check.py
 ```
 Note that the `--forked` flag is not necessary for the model tests.
 
-## Contributor License Agreement
-This project welcomes contributions and suggestions. Most contributions require you to
-agree to a Contributor License Agreement (CLA) declaring that you have the right to, and
-actually do, grant us the rights to use your contribution. For details, visit
-https://cla.opensource.microsoft.com.
+## Developer Certificate of Origin
+This project welcomes contributions and suggestions. All contributions to deepspeedai projects
+require commits to be signed off with a [Developer Certificate of Origin](https://en.wikipedia.org/wiki/Developer_Certificate_of_Origin)
+(DCO) declaring that you have the right to, and actually do, grant us the rights to use your contribution.
+
+When you submit a pull request, the DCO app will check for the presence of signed commits.
+Information about how this check works is here: https://github.com/dcoapp/app?tab=readme-ov-file#how-it-works
 
-When you submit a pull request, a CLA bot will automatically determine whether you need
-to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply
-follow the instructions provided by the bot. You will only need to do this once across
-all repos using our CLA.
+To sign commits, you will need to include `-s` when running `git commit`. For example, `git commit -s -m "Commit message"`. One note, creating PRs via the GitHub interface do not appear to include this option.  If you forget this, clicking on the failing check in your PR will point you to commands you can run to rebase and sign previous commits.
 
 ## Code of Conduct
 This project has adopted the [Microsoft Open Source Code of

diff --git a/Makefile b/Makefile
@@ -0,0 +1,23 @@
+# usage: make help
+
+.PHONY: help test format
+.DEFAULT_GOAL := help
+
+help: ## this help
+	@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n  make \033[36m<target>\033[0m\n"} /^[0-9a-zA-Z_-]+:.*?##/ { printf "  \033[36m%-22s\033[0m %s\n", $$1, $$2 } /^##@/ { printf "\n\033[1m%s\033[0m\n", substr($$0, 5) } ' $(MAKEFILE_LIST)
+	echo $(MAKEFILE_LIST)
+
+test: ## run tests
+	pytest --forked tests/unit/
+
+format: ## fix formatting
+	@if [ ! -d "venv" ]; then \
+		python -m venv venv; \
+		. venv/bin/activate; \
+		pip install pre-commit -U; \
+		pre-commit clean; \
+		pre-commit uninstall; \
+		pre-commit install; \
+		deactivate; \
+	fi
+	. venv/bin/activate && pre-commit run --files $$(git diff --name-only master) && deactivate